INDEX

Explanations

programming syntax elements such as class declarations and method definitions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

Code-related terms and identifiers

np_acts-logits-general · gemini-2.0-flash

technical terms and bulgarian words

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Kon

-0.45

 boards

-0.44

-0.42

XtraBars

-0.42

遣

-0.40

並

-0.40

wapV

-0.40

 Schla

-0.40

HStack

-0.39

listdir

-0.39

POSITIVE LOGITS

tvguidetime

0.81

 ostavi

0.76

0.75

 kasarigan

0.73

 препратки

0.72

 виправивши

0.68

AccessorTable

0.68

HomeAsUpEnabled

0.65

avares

0.64

 sclerosis

0.61

Activations Density 0.307%

programming syntax elements such as class declarations and method definitions

Code-related terms and identifiers

technical terms and bulgarian words

No Comments

No Known Activations